summaryrefslogtreecommitdiff
path: root/net/netfilter/ipvs/ip_vs_xmit.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/netfilter/ipvs/ip_vs_xmit.c')
-rw-r--r--net/netfilter/ipvs/ip_vs_xmit.c85
1 files changed, 47 insertions, 38 deletions
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 258a0b0e8..3264cb49b 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -212,19 +212,20 @@ static inline void maybe_update_pmtu(int skb_af, struct sk_buff *skb, int mtu)
ort->dst.ops->update_pmtu(&ort->dst, sk, NULL, mtu);
}
-static inline bool ensure_mtu_is_adequate(int skb_af, int rt_mode,
+static inline bool ensure_mtu_is_adequate(struct netns_ipvs *ipvs, int skb_af,
+ int rt_mode,
struct ip_vs_iphdr *ipvsh,
struct sk_buff *skb, int mtu)
{
#ifdef CONFIG_IP_VS_IPV6
if (skb_af == AF_INET6) {
- struct net *net = dev_net(skb_dst(skb)->dev);
+ struct net *net = ipvs->net;
if (unlikely(__mtu_check_toobig_v6(skb, mtu))) {
if (!skb->dev)
skb->dev = net->loopback_dev;
/* only send ICMP too big on first fragment */
- if (!ipvsh->fragoffs)
+ if (!ipvsh->fragoffs && !ip_vs_iph_icmp(ipvsh))
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
IP_VS_DBG(1, "frag needed for %pI6c\n",
&ipv6_hdr(skb)->saddr);
@@ -233,8 +234,6 @@ static inline bool ensure_mtu_is_adequate(int skb_af, int rt_mode,
} else
#endif
{
- struct netns_ipvs *ipvs = net_ipvs(skb_net(skb));
-
/* If we're going to tunnel the packet and pmtu discovery
* is disabled, we'll just fragment it anyway
*/
@@ -242,7 +241,8 @@ static inline bool ensure_mtu_is_adequate(int skb_af, int rt_mode,
return true;
if (unlikely(ip_hdr(skb)->frag_off & htons(IP_DF) &&
- skb->len > mtu && !skb_is_gso(skb))) {
+ skb->len > mtu && !skb_is_gso(skb) &&
+ !ip_vs_iph_icmp(ipvsh))) {
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
htonl(mtu));
IP_VS_DBG(1, "frag needed for %pI4\n",
@@ -256,11 +256,12 @@ static inline bool ensure_mtu_is_adequate(int skb_af, int rt_mode,
/* Get route to destination or remote server */
static int
-__ip_vs_get_out_rt(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest,
+__ip_vs_get_out_rt(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb,
+ struct ip_vs_dest *dest,
__be32 daddr, int rt_mode, __be32 *ret_saddr,
struct ip_vs_iphdr *ipvsh)
{
- struct net *net = dev_net(skb_dst(skb)->dev);
+ struct net *net = ipvs->net;
struct ip_vs_dest_dst *dest_dst;
struct rtable *rt; /* Route to the other host */
int mtu;
@@ -336,7 +337,7 @@ __ip_vs_get_out_rt(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest,
maybe_update_pmtu(skb_af, skb, mtu);
}
- if (!ensure_mtu_is_adequate(skb_af, rt_mode, ipvsh, skb, mtu))
+ if (!ensure_mtu_is_adequate(ipvs, skb_af, rt_mode, ipvsh, skb, mtu))
goto err_put;
skb_dst_drop(skb);
@@ -402,11 +403,12 @@ out_err:
* Get route to destination or remote server
*/
static int
-__ip_vs_get_out_rt_v6(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest,
+__ip_vs_get_out_rt_v6(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb,
+ struct ip_vs_dest *dest,
struct in6_addr *daddr, struct in6_addr *ret_saddr,
struct ip_vs_iphdr *ipvsh, int do_xfrm, int rt_mode)
{
- struct net *net = dev_net(skb_dst(skb)->dev);
+ struct net *net = ipvs->net;
struct ip_vs_dest_dst *dest_dst;
struct rt6_info *rt; /* Route to the other host */
struct dst_entry *dst;
@@ -484,7 +486,7 @@ __ip_vs_get_out_rt_v6(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest,
maybe_update_pmtu(skb_af, skb, mtu);
}
- if (!ensure_mtu_is_adequate(skb_af, rt_mode, ipvsh, skb, mtu))
+ if (!ensure_mtu_is_adequate(ipvs, skb_af, rt_mode, ipvsh, skb, mtu))
goto err_put;
skb_dst_drop(skb);
@@ -573,8 +575,8 @@ static inline int ip_vs_nat_send_or_cont(int pf, struct sk_buff *skb,
skb_forward_csum(skb);
if (!skb->sk)
skb_sender_cpu_clear(skb);
- NF_HOOK(pf, NF_INET_LOCAL_OUT, NULL, skb,
- NULL, skb_dst(skb)->dev, dst_output_sk);
+ NF_HOOK(pf, NF_INET_LOCAL_OUT, cp->ipvs->net, NULL, skb,
+ NULL, skb_dst(skb)->dev, dst_output);
} else
ret = NF_ACCEPT;
@@ -595,8 +597,8 @@ static inline int ip_vs_send_or_cont(int pf, struct sk_buff *skb,
skb_forward_csum(skb);
if (!skb->sk)
skb_sender_cpu_clear(skb);
- NF_HOOK(pf, NF_INET_LOCAL_OUT, NULL, skb,
- NULL, skb_dst(skb)->dev, dst_output_sk);
+ NF_HOOK(pf, NF_INET_LOCAL_OUT, cp->ipvs->net, NULL, skb,
+ NULL, skb_dst(skb)->dev, dst_output);
} else
ret = NF_ACCEPT;
return ret;
@@ -629,7 +631,7 @@ ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
EnterFunction(10);
rcu_read_lock();
- if (__ip_vs_get_out_rt(cp->af, skb, NULL, iph->daddr,
+ if (__ip_vs_get_out_rt(cp->ipvs, cp->af, skb, NULL, iph->daddr,
IP_VS_RT_MODE_NON_LOCAL, NULL, ipvsh) < 0)
goto tx_error;
@@ -656,10 +658,13 @@ int
ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
{
+ struct ipv6hdr *iph = ipv6_hdr(skb);
+
EnterFunction(10);
rcu_read_lock();
- if (__ip_vs_get_out_rt_v6(cp->af, skb, NULL, &ipvsh->daddr.in6, NULL,
+ if (__ip_vs_get_out_rt_v6(cp->ipvs, cp->af, skb, NULL,
+ &iph->daddr, NULL,
ipvsh, 0, IP_VS_RT_MODE_NON_LOCAL) < 0)
goto tx_error;
@@ -706,7 +711,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
}
was_input = rt_is_input_route(skb_rtable(skb));
- local = __ip_vs_get_out_rt(cp->af, skb, cp->dest, cp->daddr.ip,
+ local = __ip_vs_get_out_rt(cp->ipvs, cp->af, skb, cp->dest, cp->daddr.ip,
IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL |
IP_VS_RT_MODE_RDR, NULL, ipvsh);
@@ -723,7 +728,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
if (ct && !nf_ct_is_untracked(ct)) {
- IP_VS_DBG_RL_PKT(10, AF_INET, pp, skb, 0,
+ IP_VS_DBG_RL_PKT(10, AF_INET, pp, skb, ipvsh->off,
"ip_vs_nat_xmit(): "
"stopping DNAT to local address");
goto tx_error;
@@ -733,8 +738,9 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
/* From world but DNAT to loopback address? */
if (local && ipv4_is_loopback(cp->daddr.ip) && was_input) {
- IP_VS_DBG_RL_PKT(1, AF_INET, pp, skb, 0, "ip_vs_nat_xmit(): "
- "stopping DNAT to loopback address");
+ IP_VS_DBG_RL_PKT(1, AF_INET, pp, skb, ipvsh->off,
+ "ip_vs_nat_xmit(): stopping DNAT to loopback "
+ "address");
goto tx_error;
}
@@ -751,7 +757,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
ip_hdr(skb)->daddr = cp->daddr.ip;
ip_send_check(ip_hdr(skb));
- IP_VS_DBG_PKT(10, AF_INET, pp, skb, 0, "After DNAT");
+ IP_VS_DBG_PKT(10, AF_INET, pp, skb, ipvsh->off, "After DNAT");
/* FIXME: when application helper enlarges the packet and the length
is larger than the MTU of outgoing device, there will be still
@@ -794,7 +800,8 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
IP_VS_DBG(10, "filled cport=%d\n", ntohs(*p));
}
- local = __ip_vs_get_out_rt_v6(cp->af, skb, cp->dest, &cp->daddr.in6,
+ local = __ip_vs_get_out_rt_v6(cp->ipvs, cp->af, skb, cp->dest,
+ &cp->daddr.in6,
NULL, ipvsh, 0,
IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL |
@@ -812,7 +819,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
if (ct && !nf_ct_is_untracked(ct)) {
- IP_VS_DBG_RL_PKT(10, AF_INET6, pp, skb, 0,
+ IP_VS_DBG_RL_PKT(10, AF_INET6, pp, skb, ipvsh->off,
"ip_vs_nat_xmit_v6(): "
"stopping DNAT to local address");
goto tx_error;
@@ -823,7 +830,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
/* From world but DNAT to loopback address? */
if (local && skb->dev && !(skb->dev->flags & IFF_LOOPBACK) &&
ipv6_addr_type(&cp->daddr.in6) & IPV6_ADDR_LOOPBACK) {
- IP_VS_DBG_RL_PKT(1, AF_INET6, pp, skb, 0,
+ IP_VS_DBG_RL_PKT(1, AF_INET6, pp, skb, ipvsh->off,
"ip_vs_nat_xmit_v6(): "
"stopping DNAT to loopback address");
goto tx_error;
@@ -841,7 +848,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
goto tx_error;
ipv6_hdr(skb)->daddr = cp->daddr.in6;
- IP_VS_DBG_PKT(10, AF_INET6, pp, skb, 0, "After DNAT");
+ IP_VS_DBG_PKT(10, AF_INET6, pp, skb, ipvsh->off, "After DNAT");
/* FIXME: when application helper enlarges the packet and the length
is larger than the MTU of outgoing device, there will be still
@@ -967,8 +974,8 @@ int
ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
{
- struct net *net = skb_net(skb);
- struct netns_ipvs *ipvs = net_ipvs(net);
+ struct netns_ipvs *ipvs = cp->ipvs;
+ struct net *net = ipvs->net;
struct rtable *rt; /* Route to the other host */
__be32 saddr; /* Source for tunnel */
struct net_device *tdev; /* Device to other host */
@@ -984,7 +991,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
EnterFunction(10);
rcu_read_lock();
- local = __ip_vs_get_out_rt(cp->af, skb, cp->dest, cp->daddr.ip,
+ local = __ip_vs_get_out_rt(ipvs, cp->af, skb, cp->dest, cp->daddr.ip,
IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL |
IP_VS_RT_MODE_CONNECT |
@@ -1042,7 +1049,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
ret = ip_vs_tunnel_xmit_prepare(skb, cp);
if (ret == NF_ACCEPT)
- ip_local_out(skb);
+ ip_local_out(net, skb->sk, skb);
else if (ret == NF_DROP)
kfree_skb(skb);
rcu_read_unlock();
@@ -1078,7 +1085,8 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
EnterFunction(10);
rcu_read_lock();
- local = __ip_vs_get_out_rt_v6(cp->af, skb, cp->dest, &cp->daddr.in6,
+ local = __ip_vs_get_out_rt_v6(cp->ipvs, cp->af, skb, cp->dest,
+ &cp->daddr.in6,
&saddr, ipvsh, 1,
IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL |
@@ -1133,7 +1141,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
ret = ip_vs_tunnel_xmit_prepare(skb, cp);
if (ret == NF_ACCEPT)
- ip6_local_out(skb);
+ ip6_local_out(cp->ipvs->net, skb->sk, skb);
else if (ret == NF_DROP)
kfree_skb(skb);
rcu_read_unlock();
@@ -1165,7 +1173,7 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
EnterFunction(10);
rcu_read_lock();
- local = __ip_vs_get_out_rt(cp->af, skb, cp->dest, cp->daddr.ip,
+ local = __ip_vs_get_out_rt(cp->ipvs, cp->af, skb, cp->dest, cp->daddr.ip,
IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL |
IP_VS_RT_MODE_KNOWN_NH, NULL, ipvsh);
@@ -1204,7 +1212,8 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
EnterFunction(10);
rcu_read_lock();
- local = __ip_vs_get_out_rt_v6(cp->af, skb, cp->dest, &cp->daddr.in6,
+ local = __ip_vs_get_out_rt_v6(cp->ipvs, cp->af, skb, cp->dest,
+ &cp->daddr.in6,
NULL, ipvsh, 0,
IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL |
@@ -1273,7 +1282,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL |
IP_VS_RT_MODE_RDR : IP_VS_RT_MODE_NON_LOCAL;
rcu_read_lock();
- local = __ip_vs_get_out_rt(cp->af, skb, cp->dest, cp->daddr.ip, rt_mode,
+ local = __ip_vs_get_out_rt(cp->ipvs, cp->af, skb, cp->dest, cp->daddr.ip, rt_mode,
NULL, iph);
if (local < 0)
goto tx_error;
@@ -1365,8 +1374,8 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL |
IP_VS_RT_MODE_RDR : IP_VS_RT_MODE_NON_LOCAL;
rcu_read_lock();
- local = __ip_vs_get_out_rt_v6(cp->af, skb, cp->dest, &cp->daddr.in6,
- NULL, ipvsh, 0, rt_mode);
+ local = __ip_vs_get_out_rt_v6(cp->ipvs, cp->af, skb, cp->dest,
+ &cp->daddr.in6, NULL, ipvsh, 0, rt_mode);
if (local < 0)
goto tx_error;
rt = (struct rt6_info *) skb_dst(skb);
generated by cgit v1.2.3 (git 2.25.1) at 2024-06-07 08:26:43 +0000